onnxruntime/tools/ci_build/github/azure-pipelines/templates/orttraining-linux-gpu-ortmodule-test-ci-pipeline.yml
Adam Louly ee543a47f6
upgrade cuda version on ci pipelines (training CI pipelines) (#12708)
* upgrade cuda version on ci pipelines

* keeping folder name same

* keeping folder name same

* setting manual seed for primitive test case

* resolving comments

* changing atol and rtrol only for test case

Co-authored-by: Adam Louly <adamlouly@microsoft.com@orttrainingdev7.d32nl1ml4oruzj4qz3bqlggovf.px.internal.cloudapp.net>
2022-08-26 16:51:19 -07:00

39 lines
2.5 KiB
YAML

parameters:
- name: DockerImageTag
type: string
- name: BuildConfig
type: string
steps:
- bash: tools/ci_build/github/linux/docker/scripts/training/azure_scale_set_vm_mount_test_data.sh -p $(orttrainingtestdatascus-storage-key) -s "//orttrainingtestdatascus.file.core.windows.net/mnist" -d "/mnist"
displayName: 'Mount MNIST'
condition: succeededOrFailed()
- bash: tools/ci_build/github/linux/docker/scripts/training/azure_scale_set_vm_mount_test_data.sh -p $(orttrainingtestdatascus-storage-key) -s "//orttrainingtestdatascus.file.core.windows.net/bert-data" -d "/bert_data"
displayName: 'Mount bert-data'
condition: succeededOrFailed()
- bash: tools/ci_build/github/linux/docker/scripts/training/azure_scale_set_vm_mount_test_data.sh -p $(orttrainingtestdatascus-storage-key) -s "//orttrainingtestdatascus.file.core.windows.net/hf-models-cache" -d "/hf_models_cache"
displayName: 'Mount hf-models-cache'
condition: succeededOrFailed()
# Entry point for all ORTModule tests
# The onnxruntime folder is deleted in the build directory
# to enforce use of the onnxruntime wheel
# Uninstall orttraining requirements.txt and install ortmodule requirements.txt before running tests.
- script: |
docker run \
--gpus all \
--shm-size=1024m \
--rm \
--volume $(Build.SourcesDirectory):/onnxruntime_src \
--volume $(Build.BinariesDirectory)/${{ parameters.BuildConfig }}:/build \
--volume /mnist:/mnist \
--volume /bert_data:/bert_data \
--volume /hf_models_cache:/hf_models_cache \
${{ parameters.DockerImageTag }} \
bash -c "python3 -m pip uninstall -y -r /onnxruntime_src/tools/ci_build/github/linux/docker/scripts/training/requirements.txt && python3 -m pip install -r /onnxruntime_src/tools/ci_build/github/linux/docker/scripts/training/ortmodule/stage1/requirements_torch1.12.1_cu11.6/requirements.txt && python3 -m pip install -r /onnxruntime_src/tools/ci_build/github/linux/docker/scripts/training/ortmodule/stage2/requirements.txt && rm -rf /build/onnxruntime/ && python3 -m pip install /build/dist/onnxruntime*.whl && python3 -m onnxruntime.training.ortmodule.torch_cpp_extensions.install && /build/launch_test.py --cmd_line_with_args 'python orttraining_ortmodule_tests.py --mnist /mnist --bert_data /bert_data/hf_data/glue_data/CoLA/original/raw --transformers_cache /hf_models_cache/huggingface/transformers' --cwd /build" \
displayName: 'Run orttraining_ortmodule_tests.py'
condition: succeededOrFailed()
timeoutInMinutes: 60